CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

common-sdlc-metrics

Define delivery metrics from authorized observations and labeled artifact/git proxies; use for DORA, SDLC outcomes, reporting, or control bands.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, high-signal instruction skill: it gives exact commands, file paths, field names, and derivation rules while delegating bulk detail (schema, band template) to two real, clearly-signaled reference files. The main gaps are an implicitly-ordered workflow with no error-recovery loop and abstract routing/detection language that only becomes concrete in the referenced files.

Suggestions

Add an explicitly numbered step sequence in 'Use and verify' (source → schema → generate → validate → emit) with a 'only proceed when `rtk pnpm test:metrics` passes' gate to strengthen workflow_clarity.

Make band routing concrete in one line (e.g., an example of a detected breach, its tier, and the exact command or route it triggers), or point to the specific section of references/bands-template.yaml that defines it.

Include a minimal inline example of one measured row (e.g., lead time with basis/coverage/source columns) so report generation is unambiguous without opening the schema reference.

DimensionReasoningScore

Conciseness

The body is dense imperative guidance with zero padding — "Measure handoffs, not keystrokes. A missing input is unavailable, never zero; a proxy is never a measurement" — and it assumes Claude's competence by never explaining what DORA, censoring, or half-open intervals are. There is no over-explanation to trim, so it matches the 'lean and efficient' anchor rather than anchor 4.

5 / 5

Actionability

Concrete commands ("Generate the report with `rtk pnpm metrics:report --json`; run `rtk pnpm test:metrics`"), exact field names, and precise derivations ("`restored_at` minus `detected_at`", "`first_change_at` to `deployed_at`") make the core workflow executable. It falls short of 5 because band routing ("route `log` → read-only `diagnose` → `propose`") and deterministic detection mechanics remain abstract without the referenced files.

4 / 5

Workflow Clarity

The "Use and verify" section implies a clear sequence (source observations → load schema → generate → test) with an explicit validation checkpoint ("run `rtk pnpm test:metrics` for the metrics suite") and a guard ("Do not overwrite existing metrics/history artifacts"). Not 5 because steps are not explicitly ordered or numbered and no error-recovery loop is given; not 3 because a verification step is present.

4 / 5

Progressive Disclosure

References are well-signaled and one level deep ("Load [the metrics schema](references/metrics-schema.md) for the report skeleton, input contract, and derivation details" plus a References section), and both referenced files exist in references/ with no orphans. The 9KB schema and the bands template are appropriately external while the body stays an overview, matching the 'clear overview with well-signaled one-level-deep references' anchor.

5 / 5

Total

18

/

20

Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states a concrete capability with an explicit use-for clause covering a well-defined niche. Its weaknesses are breadth in the when-clause ("SDLC outcomes, reporting") and missing natural metric-name trigger terms that users commonly say.

Suggestions

Fold one or two natural metric names users actually say (e.g., "lead time", "change failure rate", "deployment frequency") into the description's use-for clause to improve trigger coverage.

Replace the broad "SDLC outcomes, reporting" phrasing with concrete situations such as "use when asked to report DORA metrics, define delivery control bands, or fill out the SDLC metrics report".

DimensionReasoningScore

Specificity

"Define delivery metrics from authorized observations and labeled artifact/git proxies; use for DORA, SDLC outcomes, reporting, or control bands" gives one concrete action with concrete sources and enumerates several specific application targets (DORA, control bands). It fits anchor 4 rather than 3 because the enumerated targets are concrete, but not 5 since coverage rests on a single verb rather than multiple specific actions.

4 / 5

Completeness

The 'what' is clear ("Define delivery metrics from authorized observations and labeled artifact/git proxies") and the 'when' is explicit ("use for DORA, SDLC outcomes, reporting, or control bands"), satisfying an explicit use clause. Not 5 because "SDLC outcomes" and "reporting" are broad and the clause lacks concrete user-situation phrasing; not 3 because the when is explicit, not weakly implied.

4 / 5

Trigger Term Quality

Natural phrases a user would say are present: "delivery metrics", "DORA", "control bands", "reporting". It matches anchor 4 — good coverage with a few natural terms missing — because common variations like "lead time", "change failure rate", and "deployment frequency" appear only in metadata triggers, not in the description itself.

4 / 5

Distinctiveness Conflict Risk

The DORA/delivery-metrics/control-bands niche is clearly distinct with specific triggers, but "reporting" and "SDLC outcomes" create minor overlap risk with general reporting or status-update skills, matching anchor 4 rather than the minimal-conflict anchor 5. It is well above anchor 3 since the dominant terms would not plausibly trigger unrelated skills.

4 / 5

Total

16

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

HoangNguyen0403/agent-skills-standard

Path

.agents/skills/common/common-sdlc-metrics/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.